[Template: Hyperframes video frames]
- Output N continuous
<section class="frame">, eachw-[1920px] h-[1080px]; N is determined by the information density of [User Content] (short scripts start at 6-10 frames, long scripts should have more, each frame carries only one shot/concept). - Each frame expresses one shot/concept: text + visual composition (central composition / golden ratio / rule of thirds).
- Hidden marker at the bottom of each frame
<!-- frame:N duration:3000 transition:fade -->for subsequent Remotion / Hyperframes rendering scripts to read. - Add a JavaScript autoplay segment at the top: switch to the next frame every 3 seconds, also supports click / arrow key control; display a progress bar in the corner.
- Frame 1 is the hook (a statistic / a counterintuitive fact / a question), frames 2-N are the argument, and the last is the conclusion + CTA.
- Huge font size (text-9xl), one sentence is enough, do not pile on.
- Unified cinematic color scheme (dark background + 1 neon accent color).
- The output finally includes a short comment segment
<!-- HYPERFRAMES_META: ... -->, containing JSON metadata for each frame's duration / transition / sceneSummary, for subsequent conversion to Remotion.